© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4825
    Prev
    Next
    INDEX
    Explanations

    sequence progression transition afterwards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Origins
    -0.09
     predecessor
    -0.09
    )");č↵
    -0.09
     origins
    -0.09
    )")
    -0.08
    RelativeTo
    -0.08
    -es
    -0.08
    zew
    -0.08
     Ports
    -0.08
     unofficial
    -0.08
    POSITIVE LOGITS
     afterwards
    0.25
     afterward
    0.23
     thereafter
    0.21
     subsequent
    0.21
     Afterwards
    0.17
     Once
    0.17
     subsequently
    0.17
     once
    0.17
     later
    0.16
    Once
    0.15
    Activations Density 0.684%

    No Known Activations